Downloads · 30 days
20
27% of all-time downloads
rLLM-FinQA-4B-MLX-4bit
snsnc/rLLM-FinQA-4B-MLX-4bit
rLLM-FinQA-4B-MLX-4bit is a text generation model from snsnc. Use it when you need the model to write or continue text. It is set up for mlx.
MLX 4-bit conversion of rLLM/rLLM-FinQA-4B for Apple Silicon. No additional training. Conversion/quantization only.
All-time downloads
73
Public
Parameters
4B
2.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.3 GB · 99%
Parameter types
How the weights are stored.
U324B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
rLLM-FinQA-4B MLX 4-bit
MLX 4-bit conversion of rLLM/rLLM-FinQA-4B for Apple Silicon.
No additional training. Conversion/quantization only.
Use
pip install mlx-lm
mlx_lm.generate \
--model snsnc/rLLM-FinQA-4B-MLX-4bit \
--max-tokens 512 \
--temp 0.1 \
--top-p 0.8 \
--prompt "Write a BigQuery SQL query to calculate daily revenue from an orders table."
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3
- Created
- Jul 1, 2026
- Updated
- Jul 1, 2026